Biomedical Engineering Letters最新文献

Early detection of breast cancer significantly improves survival rates, with nearly all patients surviving for over five years. Mathematical modeling of cancerous tissue dynamics facilitates the rapid detection of tumors. This study introduces an innovative segmented hemispherical modeling approach for breast tissue, wherein the tissues are modeled as electrical capacitors with unequal plates. The structure and performance of the proposed hemispherical model are thoroughly examined. The effective permittivity, [Formula: see text], of both individual breast tissues and the entire breast is computed using their dielectric properties. The proposed closed-form breast model is analyzed and compared with state-of-the-art methods through analytical, simulation-based, and experimental approaches. The proposed segmented hemispherical modeling technique significantly outperforms traditional cubic models, achieving substantially higher discrimination levels of 0.335 compared to 0.001 for fatty breast tissue and 0.412 compared to 0.001 for dense breast tissue. The model accurately replicates real breast anatomy and demonstrates superior efficacy in tumor detection, showing a simulated difference of 3 dB and 7 degrees in the magnitude and phase of the [Formula: see text]-parameters, respectively. Furthermore, the proposed method holds promising potential for developing an affordable and simple breast phantom fabrication method that, if adopted, could significantly facilitate research in laboratory settings. These phantoms would maintain high accuracy in replicating real breast tissue and contribute to more practical and reliable results in breast cancer detection techniques.

Magnetoencephalography (MEG) offers high spatiotemporal resolution, but its application in practical brain-computer interface (BCI) systems remains limited partially due to the need for user-specific calibration and inter-subject variability. We present a zero-calibration MEG-based BCI based on event-related fields (ERFs) by leveraging spatial filters and deep learning techniques. First, we developed an on-line ERF-based MEG BCI with a visual oddball paradigm, achieving the mean classification accuracy of 94.29% and an information transfer rate (ITR) of 20.47 bits/min. Using the resulting multi-subject dataset, we applied xDAWN spatial filtering and trained a deep convolutional neural network (DeepConvNet) to classify target versus non-target responses. To simulate real-world plug-and-play use, zero-calibration performance was evaluated using a leave-one-subject-out (LOSO) cross-validation approach. The combination of xDAWN and DeepConvNet achieved the average accuracy of 80.32% and ITR of 12.75 bits/min, respectively, demonstrating cross-subject generalization. These results underscore the feasibility of zero-calibration MEG BCIs for more practical use.

The integration of smartphones, wearable devices, and artificial intelligence (AI) has revolutionized mental health diagnostics, particularly for depression and anxiety, by enabling real-time data collection and early intervention. This review synthesizes the findings from recent studies on the use of these technologies for diagnostic precision and predictive modeling. Following the for Systematic Reviews and Preferred Reporting Items Meta-Analyses guidelines, a systematic search of PubMed, Scopus, and Web of Science was conducted for publications up to April 2025, resulting in the inclusion of 62 relevant studies. Our critical analysis revealed that, while artificial intelligence demonstrates high accuracy in detecting mental health symptoms, its performance is highly context-dependent. We examined significant challenges, including the lack of generalizability owing to disparate datasets, the critical yet often unstandardized role of feature engineering, and the "black box" nature of complex algorithms that hinder clinical trust. Addressing these limitations requires interdisciplinary collaboration, robust ethical and regulatory frameworks (e.g., GDPR and HIPAA), and scalable interpretable solutions. Future research must prioritize long-term validation, inclusivity across diverse populations, and development of explainable AI to bridge the gap between technological potential and clinical reality.

Continuous cardiac monitoring through wearable electrocardiogram (ECG) devices faces significant challenges from electromyogram (EMG) contamination and motion artifacts during daily activities. This paper introduces a novel deep learning framework employing a convolutional neural network accentuating encoder-decoder (CNNAED) architecture for robust R-peak identification in artifact-corrupted armband ECG signals. The study enrolled 10 healthy participants who underwent simultaneous 24 h monitoring using both experimental armband systems and clinical-grade Holter monitors. Time-frequency spectrograms derived from 10 s ECG segments provided input features for the CNNAED architecture. The network training objective focused on selective R-peak enhancement through amplitude accentuation while suppressing interfering signal components. Model validation employed subject-independent testing protocols emphasizing daytime recordings with increased artifact prevalence. Statistical analysis adopted paired t tests across 11,598 validated segments to assess performance improvements. Heart rate estimation accuracy showed substantial improvement, with mean absolute error decreasing from 13.26 to 9.37 beats/min following CNNAED processing, indicating 29.3% improvement with high statistical significance (p < 0.001). Root mean square of successive differences (RMSSD) showed 6.1% improvement (p < 0.001), indicating preserved cardiac timing characteristics essential for heart rate variability analysis. The proposed methodology provides a statistically robust solution for EMG artifact mitigation in wearable cardiac monitoring, enabling improved signal quality and expanded usable data availability during ambulatory conditions.

Osteoarthritis is the most common degenerative joint disease and a major cause of reduced physical function and the quality of life. Proper application of ultrasound has been proven to be effective for non-invasive osteoarthritis treatment. With a 2-D array transducer, spatial focusing of treatment pulses and three-dimensional (3-D) imaging of cartilage structures and intra-articular soft tissue are feasible for more effective treatment and diagnosis. However, supporting both imaging and therapy with a single 2-D ultrasound transducer is challenging due to the physical limitations caused by the array geometry. Given the number of active channels, increasing the element pitch can improve the lateral or elevational resolution and treatment efficacy, but introduces the grating lobe artifacts, degrading the overall image quality. To utilize a 2-D array configured with relatively large pitch elements for both 3-D imaging and low-frequency treatment, this study proposes a 3-D sub-pitch plane-wave imaging method. This method acquires channel RF data by physically translating the 2-D array transducer in the elevational and lateral directions and synthesizes all acquired RF data to reconstruct the single image, effectively maintaining the resolution while reducing grating lobe artifacts. We have demonstrated effective reduction in grating lobes through beam pattern analysis and quantitatively evaluated the imaging capabilities by Field II simulations and in-vitro experiments using a 2-D array with 8 × 8 elements centered at 2 MHz with 55% fractional bandwidth. These results could suggest that our approach may be useful in a theranostic ultrasound system supporting both treatment and diagnosis of osteoarthritic diseases.

Augmented reality (AR) has emerged as a powerful tool for enhancing human spatial awareness by overlaying digital information onto the physical world. This paper presents a review of the methodologies that enable AR-based spatial perception, with a focus on challenging environments such as underwater and disaster scenarios. We review state-of-the-art deep learning approaches for 3D data interpretation and completion, including voxel-based, point-based, and view-based methods. As part of this review, we implement an AR-enabled spatial awareness system, where the investigated deep learning solutions can be tested directly. In our approach, a robotic arm with an ultrasound sensor performs 2D scans underwater, from which a 3D point cloud of the scene is reconstructed. Using the reviewed deep learning networks, the point cloud is segmented in order to identify objects of interest, and point cloud completion is performed to infer missing structure. We report experimental results from synthetic data and underwater scanning trials, demonstrating that the system can recover and augment unseen spatial information for the user. We discuss the outcomes, including segmentation accuracy and completeness of reconstructions, as well as challenges such as data scarcity, noise, and real-time constraints. The paper concludes that, when combined with robust sensing and 3D deep learning techniques, AR enhances human spatial awareness in environments where direct perception is limited. The need for more adequate metrics to describe point clouds and for more labeled sonar datasets is discussed.

Accurate, non-invasive prediction of muscle fatigue and coordination is essential for improving exercise performance and rehabilitation strategies. This study proposed a deep learning-based algorithm that integrates surface electromyography (EMG) and markerless motion analysis to estimate muscle fatigue and intermuscular coordination during dynamic upper-limb movement. Five healthy male participants (age: 26 ± 1.73 years) performed one-arm dumbbell curls at 50% of their one-repetition maximum (1RM), during which EMG signals were collected from the biceps brachii and lateral deltoid. Muscle fatigue was evaluated using median frequency (MDF) separately for each muscle, while intermuscular coordination was quantified via the Synergy Activation Ratio (SAR), derived from non-negative matrix factorization (NMF). Markerless motion data were captured using a Kinect V2 sensor, and both EMG and motion data were used to train an LSTM model. The model demonstrated high prediction accuracy (MDF: MSE 0.0081, MAE 0.0664 for biceps; MSE 0.0102, MAE 0.0728 for deltoid; SAR: MSE 0.0366, MAE 0.1230). Results showed a decline in biceps MDF across sets, indicating localized fatigue, while the deltoid exhibited increased MDF, possibly reflecting compensatory or inefficient activation. SAR values decreased over time, suggesting fatigue-induced reorganization of muscle synergy and increased reliance on stabilizer muscles. These findings demonstrate the feasibility of using LSTM models with synchronized EMG and motion data to detect both localized fatigue and coordination changes in real-time. The proposed framework may support future applications in personalized training, fatigue monitoring, and ergonomic assessment.

The distinction between benign and malignant thoracic vertebral compression fractures (VCFs) on magnetic resonance imaging (MRI) is often subtle, and distinguishing between them is a fine-grained classification challenge. We propose a method for benign and malignant classification of thoracic VCFs based on multi-layer feature fusion and attention-guided patch reorganization to address the problem of low-level feature loss and noise associated with computing background patches when vision transformer (ViT) is applied to the task of fine-grained MRI image classification. The approach is based on the ViT architecture, which fuses low-level features with high-level features by selecting discriminative tokens using multiple layers of mutual attention weights between the classification tokens and the tokens. In addition, we incorporate an attention-guided patch recombination module that uses attention weights to select and combine patches of any two input images, which enhances the richness of the input images while reducing the noise computation. Experiments were conducted on the thoracic VCFs dataset with quantitative assessment metrics, achieving slice-level classification accuracy and AUC of 84.87% and 84.19%, respectively. Aggregating slice-level predictions, the patient-level classification accuracy reached 93.18%. Compared to other fine-grained ViT-based methods, our approach demonstrated varying improvements in slice-level accuracy, with a maximum increase of 3.65%. Ablation experiments further validated the effectiveness of the multi-layer feature fusion and patch recombination modules. The proposed MFAR-ViT utilizes the advantages of multi-layer feature fusion and patch reorganization to identify the fine-grained differences in MRI images of thoracic VCFs more efficiently, which is expected to help doctors diagnose the patient's condition quickly and accurately.

Cardiovascular disease stands as the leading cause of death globally, and substantial research has revealed its close correlation with the distribution of epicardial adipose tissue (EAT). Moreover, existing studies have demonstrated that EAT exhibits significant differences in distribution patterns and pathophysiological roles across various anatomical regions of the heart. Therefore, the quantitative analysis of EAT at different cardiac locations is crucial, and fine-grained segmentation of EAT via cardiac CT is an efficient method for obtaining the corresponding metrics. The existing computer-aided segmentation approaches typically treat EAT as a unified whole, which fails to meet the demands of nuanced diagnostics, and faces challenges such as class imbalance, thin structures, and anatomical variation, leading to low segmentation accuracy, limiting its application in cardiovascular disease risk assessment. To address these issues, we extend the existing segmentation strategy to the fine-grained segmentation of the left ventricle- (LV-), right ventricle- (RV-), and peri-atrium- (PA-) EAT, and propose the PRAEE framework based on position priors and edge enhancement. The core innovations of the proposed method are as follows: (1)Position-Prior Regularization: Considering the spatial distribution patterns of EAT in different anatomical regions, we design a regularization module that incorporates prior knowledge of typical spatial locations of various types of EAT as auxiliary constraints. This mechanism effectively guides the model to more accurately localize and differentiate EAT across anatomical regions, enabling an initial segmentation.(2)Adaptive Edge Enhancement: To further improve segmentation accuracy, we develop an edge enhancement module that explicitly extracts critical edge information through morphological operations and integrates it into the network architecture, significantly refining segmentation along boundary regions. Our approach has been validated on both a self-collected EAT dataset and the publicly available ACDC and MM-WHS datasets, demonstrating its effectiveness in enhancing fine-grained discrimination and edge detail performance.

Generative artificial intelligence (AI) models, such as diffusion models and OpenAI's ChatGPT, are transforming medicine by enhancing diagnostic accuracy and automating clinical workflows. The field has advanced rapidly, evolving from text-only large language models for tasks such as clinical documentation and decision support to multimodal AI systems capable of integrating diverse data modalities, including imaging, text, and structured data, within a single model. The diverse landscape of these technologies, along with rising interest, highlights the need for a comprehensive review of their applications and potential. This scoping review explores the evolution of multimodal AI, highlighting its methods, applications, datasets, and evaluation in clinical settings. Adhering to PRISMA-ScR guidelines, we systematically queried PubMed, IEEE Xplore, and Web of Science, prioritizing recent studies published up to the end of 2024. After rigorous screening, 145 papers were included, revealing key trends and challenges in this dynamic field. Our findings underscore a shift from unimodal to multimodal approaches, driving innovations in diagnostic support, medical report generation, drug discovery, and conversational AI. However, critical challenges remain, including the integration of heterogeneous data types, improving model interpretability, addressing ethical concerns, and validating AI systems in real-world clinical settings. This review summarizes the current state of the art, identifies critical gaps, and provides insights to guide the development of scalable, trustworthy, and clinically impactful multimodal AI solutions in healthcare.

Supplementary information: The online version contains supplementary material available at 10.1007/s13534-025-00497-1.